{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V3AL27RIUFT7EKVSGJMTCMZVHB","short_pith_number":"pith:V3AL27RI","schema_version":"1.0","canonical_sha256":"aec0bd7e28a167f22ab2325931333538417411adfc2283d7e7b860f6b1e5b81e","source":{"kind":"arxiv","id":"2505.13708","version":1},"attestation_state":"computed","paper":{"title":"Robust learning of halfspaces under log-concave marginals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Arsen Vasilyan, Jane Lange","submitted_at":"2025-05-19T20:12:16Z","abstract_excerpt":"We say that a classifier is \\emph{adversarially robust} to perturbations of norm $r$ if, with high probability over a point $x$ drawn from the input distribution, there is no point within distance $\\le r$ from $x$ that is classified differently. The \\emph{boundary volume} is the probability that a point falls within distance $r$ of a point with a different label. This work studies the task of computationally efficient learning of hypotheses with small boundary volume, where the input is distributed as a subgaussian isotropic log-concave distribution over $\\mathbb{R}^d$.\n  Linear threshold func"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.13708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2025-05-19T20:12:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd0bd40ebbe0e83c347496e5668fa2a6d2d5bfaf55c4ca7c08a9a9c2c3feb18c","abstract_canon_sha256":"b8981deab2e758214cbebcd1bb3255e5f9e2255e89316a98ab89c09aac97d692"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:49.900284Z","signature_b64":"UExZ5hKX3I5ClZSLRKyzxP0cevXq7jcz2z5ETdr+dJtFTDOkeNTcbh0Q8M/bPTdvZF99B1kvQcXeNClg3EEjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aec0bd7e28a167f22ab2325931333538417411adfc2283d7e7b860f6b1e5b81e","last_reissued_at":"2026-07-05T11:05:49.899753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:49.899753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust learning of halfspaces under log-concave marginals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Arsen Vasilyan, Jane Lange","submitted_at":"2025-05-19T20:12:16Z","abstract_excerpt":"We say that a classifier is \\emph{adversarially robust} to perturbations of norm $r$ if, with high probability over a point $x$ drawn from the input distribution, there is no point within distance $\\le r$ from $x$ that is classified differently. The \\emph{boundary volume} is the probability that a point falls within distance $r$ of a point with a different label. This work studies the task of computationally efficient learning of hypotheses with small boundary volume, where the input is distributed as a subgaussian isotropic log-concave distribution over $\\mathbb{R}^d$.\n  Linear threshold func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13708","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.13708/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.13708","created_at":"2026-07-05T11:05:49.899808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13708v1","created_at":"2026-07-05T11:05:49.899808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13708","created_at":"2026-07-05T11:05:49.899808+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3AL27RIUFT7","created_at":"2026-07-05T11:05:49.899808+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3AL27RIUFT7EKVS","created_at":"2026-07-05T11:05:49.899808+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3AL27RI","created_at":"2026-07-05T11:05:49.899808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB","json":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB.json","graph_json":"https://pith.science/api/pith-number/V3AL27RIUFT7EKVSGJMTCMZVHB/graph.json","events_json":"https://pith.science/api/pith-number/V3AL27RIUFT7EKVSGJMTCMZVHB/events.json","paper":"https://pith.science/paper/V3AL27RI"},"agent_actions":{"view_html":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB","download_json":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB.json","view_paper":"https://pith.science/paper/V3AL27RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13708&json=true","fetch_graph":"https://pith.science/api/pith-number/V3AL27RIUFT7EKVSGJMTCMZVHB/graph.json","fetch_events":"https://pith.science/api/pith-number/V3AL27RIUFT7EKVSGJMTCMZVHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB/action/storage_attestation","attest_author":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB/action/author_attestation","sign_citation":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB/action/citation_signature","submit_replication":"https://pith.science/pith/V3AL27RIUFT7EKVSGJMTCMZVHB/action/replication_record"}},"created_at":"2026-07-05T11:05:49.899808+00:00","updated_at":"2026-07-05T11:05:49.899808+00:00"}